Training a multi-exit cascade with linear asymmetric classification for efficient object detection

Peng Wang, Chunhua Shen, Hong Zheng, Zhang Ren

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

Efficient visual object detection is of central interest in computer vision and pattern recognition due to its wide ranges of applications. Viola and Jones'detector has become a de facto framework [1]. In this work, we propose a new method to design a cascade of boosted classifiers for fast object detection, which combines linear asymmetric classification (LAC) into the recent multi-exit cascade structure. Therefore, the proposed method takes advantages of both LAC and the multi-exit cascade. Namely, (1) the multi-exit cascade structure collects all the scores of prior nodes for decision making at the current node, which reduces the loss of decision information; (2) LAC considers the asymmetric nature of the node training. We also show that the multi-exit cascade better meets the assumption of LAC learning than the standard Viola-Jones'cascade, both theoretically and empirically. Experiments confirm that our method outperforms existing methods such as Viola and Jones [1] and Wu et al. [2] on the MIT+CMU test data set.

Original languageEnglish
Title of host publication2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings
Pages61-64
Number of pages4
DOIs
StatePublished - 2010
Externally publishedYes
Event2010 17th IEEE International Conference on Image Processing, ICIP 2010 - Hong Kong, Hong Kong
Duration: 26 Sep 201029 Sep 2010

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference2010 17th IEEE International Conference on Image Processing, ICIP 2010
Country/TerritoryHong Kong
CityHong Kong
Period26/09/1029/09/10

Keywords

  • Boosting
  • Cascade classifier
  • Face detection
  • Linear asymmetric classifier

Fingerprint

Dive into the research topics of 'Training a multi-exit cascade with linear asymmetric classification for efficient object detection'. Together they form a unique fingerprint.

Cite this